Work

Luthier: Bridging Auto-Tuning and Vendor Libraries for Efficient Deep Learning Inference

Year: 2025

Type: article

Abstract: This paper introduces the Automated Computing Library Tuner (Luthier), designed to optimize deep learning execution on asymmetric multi-core CPUs by selecting the most suitable kernels and distributing workloads efficiently. Utilizing existing kernel codes from inference libraries like ArmNN and XNNPack, Luthier demonstrates a significant computational advantage, achieving up to a 2.0x speed improvement in various devices and processors. Moreover, by employing achine learning techniques to reduce profiling samples, Luthier reduces tuning time by 95% compared to existing methods such as AutoTVM and Ansor. This makes Luthier a highly efficient tool in enhancing the performance and efficiency of deep learning applications on diverse hardware platforms.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.16919739

Authors: Kwon, Yongin, Cha, JooHyoung, Oh, Sehyeon, Yu, Misun, PARK, JEMAN, Lee, Jemin

Institutions: Electronics and Telecommunications Research Institute, Korea University of Science and Technology

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7077039433

FWCI:

Cites:

Cited by:

Related to: